skills/shinyorg/skills/shiny-nfc/Gen Agent Trust Hub

shiny-nfc

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides the ability to read and process NDEF data (URLs, Text, MIME) from physical NFC tags, which are untrusted external sources.
  • Ingestion points: Payload retrieval occurs via INfcTag.ReadNdef and INfcManager.Scan methods defined in SKILL.md.
  • Boundary markers: There are no instructions requiring the use of delimiters or 'ignore' instructions when the agent processes the retrieved tag content.
  • Capability inventory: The skill templates include hardware interaction capabilities such as reading, writing, and permanently locking (MakeReadOnly) tags on various platforms.
  • Sanitization: The skill does not provide logic or instructions for sanitizing or validating the contents of NDEF records before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 12:35 AM